feat(ai): separate generated model data (#6765)
This commit is contained in:
@@ -1,127 +1,36 @@
|
||||
// This file is auto-generated by scripts/generate-models.ts
|
||||
// Do not edit manually - run 'npm run generate-models' to update
|
||||
|
||||
import values from "./data/groq.json" with { type: "json" };
|
||||
import type { Model } from "../types.ts";
|
||||
|
||||
export const GROQ_MODELS = {
|
||||
"llama-3.1-8b-instant": {
|
||||
id: "llama-3.1-8b-instant",
|
||||
name: "Llama 3.1 8B",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.05,
|
||||
output: 0.08,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"llama-3.3-70b-versatile": {
|
||||
id: "llama-3.3-70b-versatile",
|
||||
name: "Llama 3.3 70B",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.59,
|
||||
output: 0.79,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-4-scout-17b-16e-instruct": {
|
||||
id: "meta-llama/llama-4-scout-17b-16e-instruct",
|
||||
name: "Llama 4 Scout 17B 16E",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.11,
|
||||
output: 0.34,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-oss-120b": {
|
||||
id: "openai/gpt-oss-120b",
|
||||
name: "GPT OSS 120B",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0.075,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-oss-20b": {
|
||||
id: "openai/gpt-oss-20b",
|
||||
name: "GPT OSS 20B",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.075,
|
||||
output: 0.3,
|
||||
cacheRead: 0.0375,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-oss-safeguard-20b": {
|
||||
id: "openai/gpt-oss-safeguard-20b",
|
||||
name: "Safety GPT OSS 20B",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.075,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-32b": {
|
||||
id: "qwen/qwen3-32b",
|
||||
name: "Qwen3-32B",
|
||||
api: "openai-completions",
|
||||
provider: "groq",
|
||||
baseUrl: "https://api.groq.com/openai/v1",
|
||||
reasoning: true,
|
||||
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"default"},
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.29,
|
||||
output: 0.59,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 40960,
|
||||
} satisfies Model<"openai-completions">,
|
||||
} as const;
|
||||
export const GROQ_MODELS = values as {
|
||||
"llama-3.1-8b-instant": Model<"openai-completions"> & {
|
||||
id: "llama-3.1-8b-instant";
|
||||
provider: "groq";
|
||||
};
|
||||
"llama-3.3-70b-versatile": Model<"openai-completions"> & {
|
||||
id: "llama-3.3-70b-versatile";
|
||||
provider: "groq";
|
||||
};
|
||||
"meta-llama/llama-4-scout-17b-16e-instruct": Model<"openai-completions"> & {
|
||||
id: "meta-llama/llama-4-scout-17b-16e-instruct";
|
||||
provider: "groq";
|
||||
};
|
||||
"openai/gpt-oss-120b": Model<"openai-completions"> & {
|
||||
id: "openai/gpt-oss-120b";
|
||||
provider: "groq";
|
||||
};
|
||||
"openai/gpt-oss-20b": Model<"openai-completions"> & {
|
||||
id: "openai/gpt-oss-20b";
|
||||
provider: "groq";
|
||||
};
|
||||
"openai/gpt-oss-safeguard-20b": Model<"openai-completions"> & {
|
||||
id: "openai/gpt-oss-safeguard-20b";
|
||||
provider: "groq";
|
||||
};
|
||||
"qwen/qwen3-32b": Model<"openai-completions"> & {
|
||||
id: "qwen/qwen3-32b";
|
||||
provider: "groq";
|
||||
};
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user